import matplotlib import seaborn as sns %matplotlib inline %config InlineBackend.figure_format = 'svg' import matplotlib.pyplot as plt plt.style.use('ggplot') import pandas as pd import numpy as np from tqdm import tqdm from sklearn.cluster import KMeans, DBSCAN from sklearn.metrics import silhouette_score from sklearn.datasets import make_blobs from sklearn.neighbors import KNeighborsClassifier from ipywidgets import interactive from collections import defaultdict import folium import re # DESIGNAMOS COLORES PARA REALIZAR CLUSTERS cols = ['#e6194b', '#3cb44b', '#ffe119', '#4363d8', '#f58231', '#911eb4', '#46f0f0', '#f032e6', '#bcf60c', '#fabebe', '#008080', '#e6beff', '#9a6324', '#fffac8', '#800000', '#aaffc3', '#808000', '#ffd8b1', '#000075', '#808080']*10

df = pd.read_csv('/content/coordenadas_sii_dummy_variables2.csv')

df = df.drop(['Unnamed: 0'], axis = 1)

df.head()

df.info('rut_completo')

m = folium.Map(location=[df.lat.mean(), df.long.mean()], zoom_start=13, tiles='OpenStreet Map') for _, row in df.iterrows(): folium.CircleMarker( location=[row.lat, row.long], radius=0.3, popup=re.sub(r'[^a-zA-Z ]+', '', row.rut_completo), color='#1787FE', fill=True, fill_colour='#1787FE' ).add_to(m)

m

X = np.array(df[['long', 'lat' ]], dtype='float64') X

from sklearn.cluster import KMeans loss=list() for i in range(1,10): kmeans=KMeans(n_clusters= i, init="k-means++") kmeans.fit(X) loss.append(kmeans.inertia_) sns.set_style("darkgrid") plt.figure(figsize=(5,5)) plt.plot(range(1,10), loss) plt.title("Método del Codo") plt.xlabel("Numero de Clusters") plt.ylabel("Perdida") plt.show()

kmeans=KMeans(n_clusters=9,init="k-means++") predicted_clusters=kmeans.fit_predict(X) silhouette_score(X,predicted_clusters)

k = 9 model = KMeans(n_clusters=k, random_state=40).fit(X) class_predictions = model.predict(X) df[f'CLUSTER_kmeans{k}'] = class_predictions

df.head(2)

def create_map(df, cluster_column): m = folium.Map(location=[df.lat.mean(), df.long.mean()], zoom_start=12, tiles='OpenStreet Map') for _, row in df.iterrows(): if row[cluster_column] == -1: cluster_colour = '#000000' else: cluster_colour = cols[row[cluster_column]] folium.CircleMarker( location= [row['lat'], row['long']], radius=0.5, popup= row[cluster_column], color=cluster_colour, fill=True, fill_color=cluster_colour ).add_to(m) return m

m = create_map(df, 'CLUSTER_kmeans9') print(f'K={k}') print(f'Silhouette Score: {silhouette_score(X, class_predictions)}') #m.save('kmeans_9_02.html') #Sirve para guardar el mapa en formato html para abrirlo externamente

m

best_silhouette, best_k = -1, 0 for k in tqdm(range(2, 10)): model = KMeans(n_clusters=k, random_state=1).fit(X) class_predictions = model.predict(X) curr_silhouette = silhouette_score(X, class_predictions) if curr_silhouette > best_silhouette: best_k = k best_silhouette = curr_silhouette print(f'K={best_k}') print(f'Silhouette Score: {best_silhouette}')

dummy = np.array([-1, -1, -1, 2, 3, 4, 5, -1]) new = np.array([(counter+2)*x if x==-1 else x for counter, x in enumerate(dummy)])

model = DBSCAN(eps=0.01, min_samples=2).fit(X) class_predictions = model.labels_ df['CLUSTERS_DBSCAN'] = class_predictions

print(f'Number of clusters found: {len(np.unique(class_predictions))}') print(f'Number of outliers found: {len(class_predictions[class_predictions==-1])}') #print(f'Silhouette ignoring outliers: {silhouette_score(X[class_predictions!=-1], class_predictions[class_predictions!=-1])}') no_outliers = 0 no_outliers = np.array([(counter+2)*x if x==-1 else x for counter, x in enumerate(class_predictions)]) #print(f'Silhouette outliers as singletons: {silhouette_score(X, no_outliers)}')

df.head()

m = create_map(df,'CLUSTERS_DBSCAN') m

df.head()

df.to_csv('Coordenadas_modelo_kmeans_dbscan.csv')